Triple
T18018204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Farringdon Without |
E431047
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Square Mile |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Square Mile | Statement: [Farringdon Without, partOf, Square Mile]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Square Mile Context triple: [Farringdon Without, partOf, Square Mile]
-
A.
Square Mile
chosen
Square Mile is the historic and financial heart of London, encompassing the small central area governed by the City of London Corporation.
-
B.
Tilemsi Valley
Tilemsi Valley is a region in northeastern Mali known for its significant paleontological sites and ancient fossil deposits.
-
C.
Metroland
Metroland was a suburban region northwest of London developed in the early 20th century and romantically marketed as an ideal commuter-belt lifestyle destination along the Metropolitan Railway.
-
D.
London Fields
London Fields is a popular public park in the London Borough of Hackney known for its open green space, lido, and vibrant community atmosphere.
-
E.
Morninghill
Morninghill is a residential suburb located near Bedfordview in the eastern part of Johannesburg, South Africa.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b9bf85c08190a40cef4c6d7b566a |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 10:24 a.m.